深度学习面试题32：循环神经网络原理(RNN)

hnyzyty

2020-07-05

关注关注

项目介绍：该项目是一个18类的文本分类任务，18类表示18个国家，每个国家也就是一个标签。每个标签下的样本是一个姓氏文本（比如：“Abakumtsev”，这是一个俄国人的常用姓氏）。简言之：根据一个姓氏，判别这个姓氏属于哪个国家。

PS：个人感觉本项目的代码里存在一些问题，经过修正后，准确率得到了提升（主要调整了一个网络架构以及加入了一个relu激活函数），我也在和作者进行沟通，详情可以查看https://github.com/pytorch/tutorials/issues/1052

思路：

■ 对每个文本拆解为字符粒度，每个字符进行独热编码，本项目中一个字符由一个含57维向量表示。那么一个长度为5的单词，就可以用一个5*57的矩阵表示。实际就是CharRNN的做法。

■ 网络的初始隐藏层置为0向量，然后一个字符一个字符的传入网络，最终对最后一个时间步的隐藏层做Softmax转换，接着使用交叉熵构造损失函数。

■ 梯度反向传播，更新网络参数。

■ 预测的时候，同训练一致。不同点是在最后一个时间步，对隐藏层做Softmax转换后，输出概率最大的类别作为最终预测的标签。

下图描绘的是RNN的矩阵表示，与前面那张图大同小异。同时这幅图更细节的展示了本项目的架构、参数以及运行中间步骤各个张量的尺寸信息，相信这对大家深入理解RNN和本项目有很大帮助。

深度学习面试题32：循环神经网络原理(RNN)

该项目的结果的混淆矩阵如下图所示，可以看到准确率还是不错的：

深度学习面试题32：循环神经网络原理(RNN)

对应代码

from __future__ import unicode_literals, print_function, division
from io import open
import glob
import os

def findFiles(path): return glob.glob(path)

print(findFiles(‘data/names/*.txt‘))

import unicodedata
import string

all_letters = string.ascii_letters + " .,;‘"
n_letters = len(all_letters)

# Turn a Unicode string to plain ASCII, thanks to https://stackoverflow.com/a/518232/2809427
def unicodeToAscii(s):
    return ‘‘.join(
        c for c in unicodedata.normalize(‘NFD‘, s)
        if unicodedata.category(c) != ‘Mn‘
        and c in all_letters
    )

print(unicodeToAscii(‘?lusàrski‘))

# Build the category_lines dictionary, a list of names per language
category_lines = {}
all_categories = []

# Read a file and split into lines
def readLines(filename):
    lines = open(filename, encoding=‘utf-8‘).read().strip().split(‘\n‘)
    return [unicodeToAscii(line) for line in lines]

for filename in findFiles(‘data/names/*.txt‘):
    category = os.path.splitext(os.path.basename(filename))[0]
    all_categories.append(category)
    lines = readLines(filename)
    category_lines[category] = lines

n_categories = len(all_categories)


print(category_lines[‘Italian‘][:5])


import torch

# Find letter index from all_letters, e.g. "a" = 0
def letterToIndex(letter):
    return all_letters.find(letter)

# Just for demonstration, turn a letter into a <1 x n_letters> Tensor
def letterToTensor(letter):
    tensor = torch.zeros(1, n_letters)
    tensor[0][letterToIndex(letter)] = 1
    return tensor

# Turn a line into a <line_length x 1 x n_letters>,
# or an array of one-hot letter vectors
def lineToTensor(line):
    tensor = torch.zeros(len(line), 1, n_letters)
    for li, letter in enumerate(line):
        tensor[li][0][letterToIndex(letter)] = 1
    return tensor

print(letterToTensor(‘J‘))

print(lineToTensor(‘Jones‘).size())

import torch.nn as nn
import torch.nn.functional as F

class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
        super(RNN, self).__init__()

        self.hidden_size = hidden_size

        self.i2h = nn.Linear(input_size + hidden_size, hidden_size)
        self.i2o = nn.Linear(hidden_size, output_size)
        self.softmax = nn.LogSoftmax(dim=1)

    def forward(self, input, hidden):
        combined = torch.cat((input, hidden), 1)
        hidden = F.relu(self.i2h(combined))
        output = self.i2o(hidden)
        output = self.softmax(output)
        return output, hidden

    def initHidden(self):
        return torch.zeros(1, self.hidden_size)

n_hidden = 128
rnn = RNN(n_letters, n_hidden, n_categories)

input = letterToTensor(‘A‘)
hidden =torch.zeros(1, n_hidden)

output, next_hidden = rnn(input, hidden)

input = lineToTensor(‘Albert‘)
hidden = torch.zeros(1, n_hidden)

output, next_hidden = rnn(input[0], hidden)
print(output)

def categoryFromOutput(output):
    top_n, top_i = output.topk(1)
    category_i = top_i[0].item()
    return all_categories[category_i], category_i

print(categoryFromOutput(output))

import random
random.seed(66)
def randomChoice(l):
    return l[random.randint(0, len(l) - 1)]

def randomTrainingExample():
    category = randomChoice(all_categories)
    line = randomChoice(category_lines[category])
    category_tensor = torch.tensor([all_categories.index(category)], dtype=torch.long)
    line_tensor = lineToTensor(line)
    return category, line, category_tensor, line_tensor

for i in range(10):
    category, line, category_tensor, line_tensor = randomTrainingExample()
    print(‘category =‘, category, ‘/ line =‘, line)

criterion = nn.NLLLoss()
learning_rate = 0.005 # If you set this too high, it might explode. If too low, it might not learn

def train(category_tensor, line_tensor):
    hidden = rnn.initHidden()

    rnn.zero_grad()

    for i in range(line_tensor.size()[0]):
        output, hidden = rnn(line_tensor[i], hidden)

    loss = criterion(output, category_tensor)
    loss.backward()

    # Add parameters‘ gradients to their values, multiplied by learning rate
    for p in rnn.parameters():
        p.data.add_(p.grad.data, alpha=-learning_rate)

    return output, loss.item()

import time
import math

n_iters = 100000
print_every = 5000
plot_every = 1000



# Keep track of losses for plotting
current_loss = 0
all_losses = []

def timeSince(since):
    now = time.time()
    s = now - since
    m = math.floor(s / 60)
    s -= m * 60
    return ‘%dm %ds‘ % (m, s)

start = time.time()
PATH = ‘./char-rnn-classification.pth‘
for iter in range(1, n_iters + 1):
    category, line, category_tensor, line_tensor = randomTrainingExample()
    output, loss = train(category_tensor, line_tensor)
    current_loss += loss

    # Print iter number, loss, name and guess
    if iter % print_every == 0:
        guess, guess_i = categoryFromOutput(output)
        correct = ‘?‘ if guess == category else ‘? (%s)‘ % category
        print(‘%d %d%% (%s) %.4f %s / %s %s‘ % (iter, iter / n_iters * 100, timeSince(start), loss, line, guess, correct))

    # Add current loss avg to list of losses
    if iter % plot_every == 0:
        all_losses.append(current_loss / plot_every)
        current_loss = 0
torch.save(rnn.state_dict(), PATH)
net = RNN(n_letters, n_hidden, n_categories)
net.load_state_dict(torch.load(PATH))


import matplotlib.pyplot as plt
import matplotlib.ticker as ticker

plt.figure()
plt.plot(all_losses)

# Keep track of correct guesses in a confusion matrix
confusion = torch.zeros(n_categories, n_categories)
n_confusion = 100000

# Just return an output given a line
def evaluate(line_tensor):
    hidden = rnn.initHidden()

    for i in range(line_tensor.size()[0]):
        output, hidden = rnn(line_tensor[i], hidden)

    return output

# Go through a bunch of examples and record which are correctly guessed
n_correct = 0
n_sum = 0
for i in range(n_confusion):
    category, line, category_tensor, line_tensor = randomTrainingExample()
    output = evaluate(line_tensor)
    guess, guess_i = categoryFromOutput(output)
    category_i = all_categories.index(category)
    confusion[category_i][guess_i] += 1
    if category == guess:
        n_correct += 1
    n_sum += 1

print("acc",n_correct/n_sum)

# Normalize by dividing every row by its sum
for i in range(n_categories):
    confusion[i] = confusion[i] / confusion[i].sum()

# Set up plot
fig = plt.figure()
ax = fig.add_subplot(111)
cax = ax.matshow(confusion.numpy())
fig.colorbar(cax)

# Set up axes
ax.set_xticklabels([‘‘] + all_categories, rotation=90)
ax.set_yticklabels([‘‘] + all_categories)

# Force label at every tick
ax.xaxis.set_major_locator(ticker.MultipleLocator(1))
ax.yaxis.set_major_locator(ticker.MultipleLocator(1))

# sphinx_gallery_thumbnail_number = 2
plt.show()

参考资料